add test file

tensnsorflow/multi.py

@@ -338,31 +338,22 @@ def get_predict(date,value_map,app_list_map,leve2_map,leve3_map):
     rdd.persist(storageLevel= StorageLevel.MEMORY_ONLY_SER)
     print(rdd.count())
 
-    # native_pre = spark.createDataFrame(rdd.filter(lambda x:x[0] == 0).map(lambda x:(x[3],x[4],x[5])))\
-    #     .toDF("city","uid","cid_id")
-    # print("native csv")
-    # native_pre.toPandas().to_csv(local_path+"native.csv", header=True)
     spark.createDataFrame(rdd.filter(lambda x: x[0] == 0)
                           .map(lambda x: (x[1], x[2], x[6], x[7], x[8], x[9], x[10], x[11],
                                           x[12], x[13], x[14], x[15], x[16], x[17], x[18],x[3],x[4],x[5]))) \
         .toDF("y", "z", "app_list", "level2_list", "level3_list", "tag1_list", "tag2_list", "tag3_list", "tag4_list",
               "tag5_list", "tag6_list", "tag7_list", "ids", "search_tag2_list","search_tag3_list","city","uid","cid_id") \
-        .repartition(1).write.format("tfrecords").save(path=path+"test_native/", mode="overwrite")
+        .repartition(1).write.format("tfrecords").save(path=path+"native/", mode="overwrite")
     print("native tfrecord done")
     h = time.time()
     print((h-f)/60)
 
-    # nearby_pre = spark.createDataFrame(rdd.filter(lambda x: x[0] == 1).map(lambda x: (x[3], x[4], x[5]))) \
-    #     .toDF("city", "uid", "cid_id")
-    # print("nearby csv")
-    # nearby_pre.toPandas().to_csv(local_path + "nearby.csv", header=True)
-
     spark.createDataFrame(rdd.filter(lambda x: x[0] == 1)
                           .map(lambda x: (x[1], x[2], x[6], x[7], x[8], x[9], x[10], x[11],
                                           x[12], x[13], x[14], x[15], x[16], x[17], x[18],x[3],x[4],x[5]))) \
         .toDF("y", "z", "app_list", "level2_list", "level3_list", "tag1_list", "tag2_list", "tag3_list", "tag4_list",
               "tag5_list", "tag6_list", "tag7_list", "ids", "search_tag2_list","search_tag3_list","city","uid","cid_id") \
-        .repartition(1).write.format("tfrecords").save(path=path + "test_nearby/", mode="overwrite")
+        .repartition(1).write.format("tfrecords").save(path=path + "nearby/", mode="overwrite")
     print("nearby tfrecord done")